Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1014 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1372. Min Act: -0.0002

Data Index: 1572848 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1300. Min Act: -0.0003

Data Index: 1505011 (Python Code)

Max Activating Token Index: 558

Text #2

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1407697 (Python Code)

Max Activating Token Index: 927

Text #3

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1379997 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1641391 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1428305 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1397515 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1439077 (Python Code)

Max Activating Token Index: 519

Text #8

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1567526 (Python Code)

Max Activating Token Index: 838

Text #9

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1528117 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1445044 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1509319 (Python Code)

Max Activating Token Index: 436

Text #12

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1585644 (Python Code)

Max Activating Token Index: 860

Text #13

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1455296 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1594895 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1490001 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1423160 (Python Code)

Max Activating Token Index: 581

Text #17

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1539294 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1508693 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1480714 (Python Code)

Max Activating Token Index: 875